Mobility Enhancement for Elderly

21 Oct 2014  ·  Ramviyas Parasuraman ·

Loss of Mobility is a common handicap to senior citizens. It denies them the ease of movement they would like to have like outdoor visits, movement in hospitals, social outgoings, but more seriously in the day to day in-house routine functions necessary for living etc. Trying to overcome this handicap by means of servant or domestic help and simple wheel chairs is not only costly in the long run, but forces the senior citizen to be at the mercy of sincerity of domestic helps and also the consequent loss of dignity. In order to give a dignified life, the mobility obtained must be at the complete discretion, will and control of the senior citizen. This can be provided only by a reasonably sophisticated and versatile wheel chair, giving enhanced ability of vision, hearing through man-machine interface, and sensor aided navigation and control. More often than not senior people have poor vision which makes it difficult for them to maker visual judgement and so calls for the use of Artificial Intelligence in visual image analysis and guided navigation systems. In this project, we deal with two important enhancement features for mobility enhancement, Audio command and Vision aided obstacle detection and navigation. We have implemented speech recognition algorithm using template of stored words for identifying the voice command given by the user. This frees the user of an agile hand to operate joystick or mouse control. Also, we have developed a new appearance based obstacle detection system using stereo-vision cameras which estimates the distance of nearest obstacle to the wheel chair and takes necessary action. This helps user in making better judgement of route and navigate obstacles. The main challenge in this project is how to navigate in an unknown/unfamiliar environment by avoiding obstacles.

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here